Artificial Intelligence for Applications in Neurology 

Many tasks in medicine still involve substantial manual work. In many cases there is strong potential for intelligent automation by Artificial Intelligence (AI), leading possibly to a reduction in costs and man-hours, while increasing the quality of clinical service. In this talk, we will consider applications of AI in the domain of neurology. We are developing a low cost validated system to automatically interpret EEG via remote access. Diagnosis and management of neurological disorders rely on visual review of EEG data by specialized physicians. As the duration of EEG recordings ranges from 30 minutes to several weeks, the visual review is time consuming, and accounts for approximately 80% of total cost associated with EEG reading. Our system has the potential to reduce expenses associated with EEG testing and allows physicians to devote more quality time to their patients. One of the applications that we have explored so far is diagnosis of epilepsy of EEG. In this talk, we will show numerical results on large EEG datasets of epilepsy patients and healthy control subjects for multiple centers.